update repo

This commit is contained in:
嘉渊 2023-05-12 16:40:29 +08:00
parent 4c87b59319
commit 57b47cb826

View File

@ -34,14 +34,14 @@ fi
# validate utt-key list, IC0803W0380 is a bad utterance
awk '{print $1}' $corpus/wav.scp | grep -v 'IC0803W0380' > $tmp/wav_utt.list
awk '{print $1}' $corpus/trans.txt > $tmp/trans_utt.list
tools/filter_scp.pl -f 1 $tmp/wav_utt.list $tmp/trans_utt.list > $tmp/utt.list
utils/filter_scp.pl -f 1 $tmp/wav_utt.list $tmp/trans_utt.list > $tmp/utt.list
# wav.scp
awk -F'\t' -v path_prefix=$corpus '{printf("%s\t%s/%s\n",$1,path_prefix,$2)}' $corpus/wav.scp > $tmp/tmp_wav.scp
tools/filter_scp.pl -f 1 $tmp/utt.list $tmp/tmp_wav.scp | sort -k 1 | uniq > $tmp/wav.scp
utils/filter_scp.pl -f 1 $tmp/utt.list $tmp/tmp_wav.scp | sort -k 1 | uniq > $tmp/wav.scp
# text
tools/filter_scp.pl -f 1 $tmp/utt.list $corpus/trans.txt | sort -k 1 | uniq > $tmp/text
utils/filter_scp.pl -f 1 $tmp/utt.list $corpus/trans.txt | sort -k 1 | uniq > $tmp/text
# copy prepared resources from tmp_dir to target dir
mkdir -p $dir